# wget https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0/resolve/main/model_config.json
# wget https://huggingface.co/IDEA-Emdoor/DistilCodec-v1.0/resolve/main/g_00204000

from distilcodec import DistilCodec, demo_for_generate_audio_codes
from transformers import AutoTokenizer, AutoModelForCausalLM

codec_model_config_path='model_config.json'
codec_ckpt_path = 'g_00204000'

codec = DistilCodec.from_pretrained(
    config_path=codec_model_config_path,
    model_path=codec_ckpt_path,
    use_generator=True,
    is_debug=False).eval()

tokenizer = AutoTokenizer.from_pretrained('mesolitica/Malaysian-TTS-1.7B-v1')
model = AutoModelForCausalLM.from_pretrained('mesolitica/Malaysian-TTS-1.7B-v1', torch_dtype = 'auto').cuda()

Generate,

bash

import soundfile as sf
import re
from tqdm import tqdm

speakers = [
    'husein',
    'idayu',
    'singaporean',
    'DisfluencySpeech',
    'singlish-speaker2050',
    'singlish-speaker2202',
    'haqkiem',
]

string = 'IC saya adalah, sembilan enam, kosong tiga, satu empat, one, one, one, one, A, B, C, D, D, yes, Husein is very cute, cute, cute.'

for s in tqdm(speakers):

    left = s +': ' + string
    prompt = f'<|im_start|>{left}<|speech_start|>'
    
    generate_kwargs = dict(
        **tokenizer(prompt, return_tensors = 'pt', add_special_tokens = False).to('cuda'),
        max_new_tokens=1024,
        temperature=0.7,
        do_sample=True,
        repetition_penalty=1.1,
    )
    generation_output = model.generate(**generate_kwargs)
    speech_token = tokenizer.decode(generation_output[0]).split('<|speech_start|>')[-1].replace('<|endoftext|>', '')
    numbers = re.findall(r'speech_(\d+)', speech_token)
    d = list(map(int, numbers))
    y_gen = codec.decode_from_codes(
        d,
        minus_token_offset=False
    )
    sf.write(f'{s}.mp3', y_gen[0, 0].cpu().numpy(), 24000)

Output,

Only singlish-speaker2202 and haqkiem had to generate 2 times to get better output that follow exact text input.

Limitation

This model trained on normalized text, so if you have text such as 123, you have to normalize it first to become one two three or one hundred twenty three or satu dua tiga or seratus dua puluh tiga. Feel free to use Malaya for normalization, Malaya support Malay and English normalization, read more at https://github.com/mesolitica/malaya/issues/247#issuecomment-3030313021
The repetitive pronunciation dataset does not consistently use commas for pauses. For example, A, A, A, A, B, B in our recordings is spoken as A A A A B B. We have no intention to improve it due to cost, but continue finetune using proper dataset should able to solve it.

Source code

Source code at https://github.com/mesolitica/malaya-speech/tree/master/session/qwen-tts

Acknowledgement

Special thanks to https://www.sns.com.my and Nvidia for 1x H100!